Peer Revenue Past citations are no guarantee of future returns

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science

cs Watch Computer Science

Tuesday 22 September

Artificial Intelligence

Escaping Python Dependency Hell: A Hybrid Replay-and-Repair Pipeline for Python Dependency Resolution

Veronica Poweska, Ariana Oyanguren, Jessica Pourleyli et al. (+2 more)

Dependency conflicts in Python ecosystems arise from incompatible version constraints, missing packages, and undocumented compatibility relationships, causing many real-world code snippets to fail at execution. This paper presents PLLM+, a hybrid dependency-repair pipeline evaluated on the HG2.9K benchmark of 2,891 dependency-failing snippets. PLLM+ prioritizes inexpensive deterministic steps before invoking LLM-based repair: static AST-based interpreter inference, replay of historically successful dependency configurations from the competition-provided solutions database, and live PyPI validation of candidate package versions. When these steps do not resolve a case, the system falls back to a structured LLM-based repair loop with typed error classification and Proposer/Critic agents. On HG2.9K, PLLM+ solves 1,500 out of 2,891 snippets, compared with 1,169 solved by the PLLM baseline. It also reduces average runtime from 368.7 to 71.8 seconds per snippet. Most successful fixes come from replaying known configurations: 1,495 of the 1,500 successful fixes are produced by the solutions database, while the LLM fallback accounts for 5 additional fixes. These results suggest that, in this benchmark setting, deterministic reuse of previously validated dependency configurations is a simple and effective strategy, with LLM-based repair serving as a secondary fallback for cases not covered by prior solutions.
Read the full abstract

All authors Veronica Poweska, Ariana Oyanguren, Jessica Pourleyli, Sourena Khanzadeh, Manar Alalfi

Machine Learning · Cross-listed from math.ST

Rolling Conformal Prediction in Sequential Model Training

Chen Cheng, Ruiting Liang and Rina Foygel Barber

We introduce Rolling Conformal Prediction (rolling-CP), a distribution-free predictive inference method for the setting of sequential model training. Specifically, given a data stream $(X_1,Y_1),(X_2,Y_2),\dots$, at each time $n$ the trained model may depend on the observed history $\{(X_i,Y_i)\}_{i<n}$. This setting arises naturally in modern sequential training, including one-pass training over massive datasets and continual fine-tuning or test-time adaptation of language models during deployment. Rolling-CP first calibrates each incoming observation against the current predictor and then rolls it into future training. In this way, we avoid the need for data splitting. Remarkably, although the models at times $n=1,2,\dots$ may have entirely different properties and accuracy levels, for exchangeable data it is nonetheless possible to establish a guarantee of marginal coverage, with a familiar universal factor-two guarantee (a worst case guarantee of $1-2\alpha$ coverage, as compared to the target level $1-\alpha$), without any assumptions of stability or any restrictions on the model training process. For i.i.d. data streams, we further prove high-probability training-conditional validity uniformly over time; under stability conditions, coverage guarantees sharpen towards $1-\alpha$. Numerical experiments on sequential regression, multiclass SGD, and one-pass neural-network training further demonstrate the practical effectiveness of rolling-CP.
Read the full abstract

Information Theory · Cross-listed from math.PR

Geometric mean quantization via adaptive approximation

Marc Kesseböhmer and Aljoscha Niemann

Let $\nu$ be a compactly supported Borel probability measure on $\mathbb R^{d}$ with $\nu(B(x,r))\leq Cr^{a}$ for some $a>0$. Refine a dyadic cube exactly when its mass is at least $t$, and let $\mathcal{L}_{\nu}(t)$ be the mean depth at which this refinement stops. We show that the lower and upper geometric-mean quantization dimensions of $\nu$ are the lower and upper limits of $\log(1/t)/\mathcal{L}_{\nu}(t)$. The dimension exists precisely when $(q-1)\sum_{Q}\nu(Q)^{q}$, summed over all dyadic cubes, converges as $q\downarrow1$, and it is then determined by this limit. The mass-threshold formula yields harmonic integral bounds in terms of the local dimensions and encloses entropy and quantization dimensions in a common spectral interval. Convergence in law of the local information rates is equivalent to convergence of the rescaled spectra in a window of width $1/k$ around $q=1$; the two dimensions are then the arithmetic and the harmonic mean of the limit law, and we quantify their difference by sharp bounds and variance identities. Without any convergence assumption, vanishing threshold variance still forces equality of the corresponding lower and upper dimensions. Bernoulli mixtures realise every local-dimension law with compact support in $(0,1]$, and a regime-switching example separates convergence in law from almost-everywhere convergence.
Read the full abstract

Computation and Language

Classifying Interpretive Canons at the Sentence Level: A Benchmark from the German Federal Constitutional Court

Felix Ringe

Judicial reasoning remains challenging for large language models (LLMs) to analyze. This paper contributes a sentence-level benchmark for evaluating the ability of LLMs to classify interpretive canons as articulated by Larenz in the tradition of Savigny. Our contributions are threefold. First, we operationalize this conception of interpretation as classification criteria. Second, we provide a dataset of decisions of the German Federal Constitutional Court annotated at the sentence level. Third, we report baseline evaluations of four LLMs from three model families under expert hand-written prompts, compared against prompts optimized with Genetic-Pareto (GEPA). Mean F1 over the seven binary subtasks clusters between 70.4 and 79.2 across models, with grammatical interpretation usually the easiest canon to identify and systematic interpretation usually the hardest; under the tested configuration, GEPA-optimized prompts do not systematically outperform the hand-written ones, suggesting that the expert prompts provide a meaningful baseline.
Read the full abstract

Computation and Language

Recognized but Not Produced: A Generation Benchmark for Culturally Specific Kinship Terms

Sahil Pardasani and Madhusudan Singh

Current literature evaluates large language models (LLMs) on multilingual kinship understanding using multiple choice benchmarks, treating it as a recognition problem. We instead prompt five open weight LLMs to generate kinship terms in three non Western languages (Hindi, Tamil, and Korean) across two communicative tasks and pair this with a matched option-supported selection baseline. On identical relation language cells, GPT OSS120B selects the correct term in 90.67% of 75 valid cells but produces an accepted term in 36.00% of the corresponding attempts; Llama 3.370B shows the same pattern (77.92% versus 24.24%). Since the four-option condition displays the candidate terms and does not require script production, the difference is interpreted as an evaluation format gap rather than direct proof that lexical knowledge is intact. On explicitly specified L3 prompts, accuracy varies sharply, from GLM-5.1 at 72.29% to Llama-3.370B at 24.24%. The paternal-lineage advantage is language specific; it is large in Hindi but weak or reversed in Korean, while Tamil shared-term pairs provide a control for measurement variation. These results show that culturally specific kinship generation remains difficult even when the relationship is explicitly stated and motivate generation-based evaluation alongside multiple-choice testing.
Read the full abstract

Neural and Evolutionary Computing

The Computational Value of Sensory-Aligned Receptive Fields Depends on Neuronal Expressivity

Agnese Adorante, Aaron Spieler and Anna Levina

Biological sensory neurons have selective receptive fields organized along meaningful stimulus coordinates, such as frequency, motion direction, or retinotopic position. Such structure may arise from efficient coding and biological constraints on activity, connectivity, and wiring, as computational studies of simple neurons have shown across modalities. This raises a question: do structured receptive fields confer a computational advantage beyond resource efficiency itself, and does this advantage persist when individual neurons are highly expressive? We address this question in recurrent networks of Expressive Leaky Memory neurons, where we can independently vary neuronal complexity and the organization of feed-forward receptive fields. Across auditory and event-based visual classification tasks, receptive fields aligned with a task-relevant sensory coordinate improve test accuracy relative to budget-matched random receptive fields. This advantage disappears when sensory coordinates are scrambled, or when receptive fields follow task-irrelevant coordinates, showing that the benefit comes from alignment with task geometry rather than restricted connectivity alone. Increasing neuronal complexity reduces the performance advantage of structured receptive fields. Finally, generic synaptic sparsity regularization induces input selectivity and partially recovers performance, but remains substantially below explicitly structured receptive fields, suggesting that sparsity alone is insufficient to recover the full computational benefit of task-aligned receptive fields. Together, our results show that appropriate receptive fields can serve as a computational prior beyond sparsity itself, and that their value depends on the computational expressivity of individual neurons.
Read the full abstract

Data Structures and Algorithms

Fast Geometric Spanners via Approximate Nearest Neighbor Search

Alexandr Andoni, Manuel Paez, Krish Singal et al. (+1 more)

We study the problem of constructing metric spanners in general metric spaces in subquadratic time when given blackbox access to a fast algorithm for batch approximate nearest neighbor search. In particular, we show the following results for any metric space $\mathsf{M} = ([n], \mathsf{d})$ with aspect ratio $\Delta$ admitting a $c$-approximate batch nearest neighbor search algorithm with runtime $\tau_{\mathsf{M}}(n)$, (1) There exists an algorithm that, for any $k \in \mathbb{N}$, constructs an $O(c k)$-distortion spanner with $\tilde{O}(kn^{1+1/2k} \log \Delta)$ edges and runs in time $\tilde{O}(\tau_{\mathsf{M}} \cdot k n^{1/k} \log \Delta)$. (2) Any algorithm that learns at most $o(n^{1+1/k}/k)$ pairwise distances by querying a distance oracle and a blackbox batch nearest neighbor search oracle necessarily incurs $\Omega(c k)$ distortion. Our results entail that (truly) sub-quadratic time algorithms for spanner construction is equivalent to subquadratic time BANN (up to constant-factor losses). As a further application, we use our fast spanner constructions to obtain a fast algorithm for approximating the Wasserstein distance $\mathsf{W}_q$, for all $q > 1$, over any metric space admitting an efficient batch approximate nearest neighbor search algorithm. Together with recent new efficient algorithms for approximate nearest neighbor search in $\ell_p$ spaces, for $p > 2$, our results entail the first subquadratic time algorithms for spanner construction (with the stated size-distortion tradeoff) and $\mathsf{W}_q$ distance approximation over these metric spaces.
Read the full abstract

All authors Alexandr Andoni, Manuel Paez, Krish Singal, Tian Zhang

Computers and Society

Asset-Class Specific Sustainability Disclosure: Lessons Learned from the EU MiCA Regulation

Ulrich Gallersdörfer, Lena Klaaßen, Christoph Kreiterling et al. (+1 more)

Sustainability disclosure in the European Union has so far focused on corporate reporting and sustainability information attached to traditional financial products. Crypto-assets, with consensus-mechanism-driven environmental externalities and fragmented issuer structures, largely fell through this disclosure architecture. The EU Markets in Crypto-Assets Regulation (MiCA) introduces the first EU-wide, asset-class-specific sustainability disclosure regime for crypto-assets by mandating standardised sustainability indicators for both issuers and crypto-asset service providers. Drawing on a policy and legal analysis of MiCA and its Level 2 measures, and on early implementation evidence from public registers and market practice, this paper shows how the policy approach shifted from debates about restricting energy-intensive consensus mechanisms to a transparency regime built on quantitative metrics, machine-readable reporting, and methodological alignment with the broader EU sustainable-finance framework. The paper also highlights practical frictions in implementation, including data gaps, responsibility allocation between issuers and intermediaries, and cross-border supervisory fragmentation. The overview and quantitative summary of the ESMA Interim MiCA Register in this paper may also provide valuable information to regulators and market participants in the context of the European Commission's 2026 targeted consultation on the review of MiCA, including its specific question on environmental and sustainability reporting.
Read the full abstract

All authors Ulrich Gallersdörfer, Lena Klaaßen, Christoph Kreiterling, Christian Stoll

Artificial Intelligence

Which Objectives Need a Dial? Predicting Objective Conflict and Covering Trade-offs in Steerable Pluralistic Alignment

David Tsoi and Esra Dönmez

People hold diverse, sometimes conflicting values, so no single aligned model can satisfy everyone. Pluralistic alignment therefore calls for steerable models that can balance competing objectives differently. Multi-Objective Direct Preference Optimization (MODPO) does this by using an objective weight to span a continuum of trade-offs. We study two questions: when can one model improve two objectives simultaneously, and how can many trade-offs be covered without training a separate model for each? Across seven objective pairs from HelpSteer and UltraFeedback, two pre-training measurements predict whether objectives align or conflict for human-annotated data, but not for AI-annotated data, where response length and repetition confound reward-model scores. For broader trade-off coverage, selecting the nearest trained model and merging model parameters both help, but neither consistently matches direct training. These findings yield practical guidance for building steerable models that serve diverse preferences.
Read the full abstract

Artificial Intelligence

Building Socio-Affective Artificial Intelligence for Interactive Multi-Agent Simulations

David Berga

The objective of this article is to provide design principles and a software architecture for enabling interaction between humans and multiple agents in simulated dynamic worlds. This connects the current era of general artificial intelligence (AI/AGI) with the proliferation of transformer-based conversational agents and the increased computational capabilities. Given an overview of current and previous multi-agent theories of mind (socially and affectively-aware agents), the existence of an integrative design of agent interactions with themselves and with humans must be crucial for understanding how to create sustainable and governance in future human-agent reasoning systems. In this work is presented a software "AGIMUD" that integrates: A. socially-aware reasoning and emotion in agent behavior and interaction, B. a design of human multimodal scheme for human users, artificial agents and simulated worlds, and C. distributing the AI processing through the network to enable multiple autonomous agents. These integrations allow the dynamic world recreation as multi-user dungeons (MUDs) where both agents and humans can interact simultaneously in real time. Find the code online in https://github.com/dberga/AGIMUD.
Read the full abstract

Computation and Language

Experts Rise Where LLMs Disagree: Using Cross-Model Disagreement to Target Expert Effort in LLM Codebook Revision for Large-Scale Annotation

Zeyu He, Zhuqian Zhou, Kirk Vanacore et al. (+2 more)

Large-scale text annotation brings expert insight to millions of documents, often through a codebook that AI annotators follow. Developing a robust codebook, however, takes months. Large language models (LLMs) could speed this process by applying an early codebook to the data, surfacing cases with strong LLM disagreement, and eliciting expert feedback to address them. We examined three ways experts can provide feedback for LLM codebook revision: (i) editing LLM-generated revisions driven by cross-LLM disagreement (Codebook Verifying), (ii) answering questions about LLM disagreements (Question Answering), and (iii) labeling disagreement cases with rationales (Rationale Labeling). Experiments on thousands of tutoring-session transcripts show that Rationale Labeling yielded the highest LLM-labeling accuracy (64.9%) against expert labels, outperforming the expert-revised codebook (57.8%). The best Question Answering setting also outperformed it (60.5%). Our work shows that LLMs can be used to strategically target expert attention, shortening months of codebook revision to days without sacrificing labeling performance.
Read the full abstract

All authors Zeyu He, Zhuqian Zhou, Kirk Vanacore, Rene F. Kizilcec, Ting-Hao 'Kenneth' Huang

Computer Vision

nnFoundation: 3D Foundation Models for Radiology

Constantin Ulrich Harsy, Tassilo Wald, Karol Gotkowski et al. (+80 more)

Radiological artificial intelligence has advanced rapidly, yet most systems remain narrowly task-specific, data-intensive, and fragile under domain shift. Foundation models promise more transferable and data-efficient solutions, but existing approaches are limited in scale, evaluated narrowly, and often assume that a single pretrained model can support diverse downstream tasks. Here we present nnFoundation, complementary convolutional and transformer-based 3D radiological foundation models. Developed within the Human Radiome Project (THRP), nnFoundation is trained on 2.1 million CT, MRI, and PET image volumes from 125 institutional and public datasets. We evaluate them across 108 tasks spanning segmentation, detection, classification, report generation, and image retrieval, including evaluations under domain shift, by external partners and in low-data and low-compute regimes. Across all task types, our convolution- and transformer-based nnFoundation models consistently outperform both prior 3D foundation models and training from scratch, establishing state-of-the-art performance for radiological imaging. However, performance follows a consistent task-dependent structure: the convolutional nnFoundation model dominates spatially localized tasks, whereas the transformer-based nnFoundation model excels in tasks requiring global semantic reasoning and in frozen-feature settings. Dynamically aligning the foundation model topology with the dataset characteristics post-hoc further improves transfer across heterogeneous 3D settings. These results show that transferable 3D radiological performance is governed not by a single universal model, but by the interplay of scalable pretraining, complementary architectures, and dataset-aware adaptation. We release nnFoundation models integrated into nnU-Net and nnDetection, enabling immediate application across established radiology workflows.
Read the full abstract

All authors Constantin Ulrich Harsy, Tassilo Wald, Karol Gotkowski, Yannick Kirchhoff, Marcel Knopp, Maximilian Rokuss, Elisa Stegmeier, Philipp Schader, Dasha Trofimova, Raphael Stock, Kim-Celine Kahl, Stephen Schaumann, Selen Erkan, David Zimmerer, Stefan Denner, Moritz Langenberg, Sebastian Ziegler, Katharina Eckstein, Maximilian Fischer, Jonathan Suprijadi, Bálint Kovács, Benjamin Hamm, Anand Deshpande, Dimitrios Bounias, Nico Disch, Shuhan Xiao, Jessica Kächele, Jan Sellner, Rajesh Baidya, Jeremias Traub, Lars Krämer, Maximilian Zenk, Tim Rädsch, Stefan Dvoretskii, Robin Peretzke, Jonathan Deissler, Alexandra Ertl, Partha Ghosh, Kris Dreher, Stefan Dinkelacker, Annika Reinke, Evangelia Christodoulou, Numan Saeed, Yoland Savriama, Santiago Estrada, David Kügler, Laura Alexandra Daza Barragan, Cristina Isabel Gonzalez Osorio, Jan Peeken, Michael Baumgartner, Marvin Teichmann, Guillaume Chabin, Matthias Kirchler, Valentin Koch, for the ALFA study, Markus Hohenhaus, Dimitri Koslov, Nina Decker, Mohammad Yaqub, Arnd Heuser, Martin Reuter, Julia A. Schnabel, Tobias Heimann, Florin Ghesu, Paul Brachmann, Claus P. Heußel, Alexander Radbruch, Gianluca Brugnara, Aditya Rastogi, Martha Foltyn-Dumitru, Heinz-Peter Schlemmer, Ignaz Reicht, Julius C. Holzschuh, Michael Bach, Bram Stieltjes, Kai Schlamp, Lena Maier-Hein, Marco Nolden, Ralf Floca, Paul F. Jäger, Philipp Vollmuth, Fabian Isensee, Klaus H. Maier-Hein

Computer Vision

A 3D Pose-Based Ensemble Framework for Cricket Shot Classification and Automated Biomechanical Analysis

Sourav Shome, M.D. Ashiquzzaman Rahad and Rameswar Debnath

Cricket is one of the most celebrated sports world-wide, and technological advancement has become deeply embedded in how the modern game is analyzed and coached. Cricket shot classification and automated performance analysis add a further dimension to this trend. Traditional approaches rely on RGB video features or static images, which are sensitive to environmental variations such as camera angle, lighting, and background clutter, and often fail to capture the underlying biomechanics of batting actions. In this paper, we propose a system to improve cricket coaching that takes raw video data, extracts batsmen from video frames using YOLO, and extracts 3D pose data from video frames using MeTRAbs. The system produces sequential skeletal pose data of 30 body points and captures the biomechanical features of a batsman. As part of the system, we also propose a deep learning ensemble for shot classification of four shots: flick, pull, defense, and drive. The ensemble performed well, compared to existing classification works, achieving 97.68% accuracy. In addition, we analyzed the misclassification rates to identify cases where shots were incorrectly classified and examined their possible causes. Our proposed system allows novice players to obtain useful feedback, such as important joint angles relative to expert batsmen, which can also be useful for injury prevention. The shot classifier also helps track class-wise shots over time for further analysis. In addition to novice players, coaches can use the system for player evaluation.
Read the full abstract

Information Retrieval

Distilling Lexical Product Associations into Deep Transformers: An Extreme Multi-Label Approach for Natural Language E-Commerce Search

Sunnidhya Roy and Samarpita Bhaumik

Traditional e-commerce search platforms rely heavily on inverted indices and token-level lexical matching algorithms (e.g., BM25 and TF-IDF), which frequently fail on conversational, intent-driven, or paraphrased user queries – the classic vocabulary mismatch problem. We formulate conversational product recommendation as an Extreme Multi-Label Classification (XMLC) problem over an e-commerce catalog of N = 54,000 products spanning 27 balanced retail categories from the Amazon Reviews '23 benchmark. Using a pre-trained DistilBERT transformer encoder, we distill dense item-to-item similarity topologies (generated via TF-IDF cosine similarity over cumulative metadata with K = 50 nearest neighbours) into a deep contextual representation via a pseudo-label knowledge distillation framework. Evaluated on an exact 85/15 train/validation split (8,089 held-out products across C = 53,923 output classes) with strict self-exclusion enforced, the DistilBERT neural student achieves P@1 = 93.15%, P@5 = 90.08%, NDCG@10 = 0.8845, and MRR@10 = 0.9545, closely recovering the empirical ceiling established by the corrected TF-IDF teacher (P@1 = 98.10%, NDCG@10 = 0.9419, MRR@10 = 0.9882). Furthermore, a qualitative benchmark across ten structured natural language query archetypes – encompassing situational, cross-category, paraphrased, and negative-constraint queries – demonstrates that the transformer student generalises substantially beyond keyword matching, successfully resolving implicit user intent where lexical models fail completely. Finally, we analyse the architectural and memory scalability trade-offs of extreme classification projection layers at industrial catalog scale (> 10^6 items) and present a concrete deployment trajectory toward Dual-Encoder (Two-Tower) vector search. Code: https://github.com/Sunnidhya/Distilling-Lexical-Product-Associations-into-Deep-Transformers.
Read the full abstract

Computer Vision

Cross-Modal Contrastive Learning from Histopathology and CT for Automated Renal Cell Carcinoma Grading

Amit Das, Tanmay Shukla, Naofumi Tomita et al. (+9 more)

Background: Clear cell renal cell carcinoma (ccRCC) exhibits substantial clinical heterogeneity, and accurate grade assessment is essential for risk stratification and treatment planning. However, conventional grading requires invasive tissue sampling. We developed RCC-Align, a cross-modal contrastive learning framework that leverages paired histopathology and computed tomography (CT) data during training to improve noninvasive CT-based ccRCC grade prediction. Methods: RCC-Align aligns paired whole-slide histopathology images (WSIs) and CT scans through contrastive cross-modal objectives, transferring grade-discriminative information from microscopic tissue morphology to macroscopic radiologic representations. The framework was trained and evaluated on paired TCGA and CPTAC cohorts using patient-level five-fold cross-validation. Performance for low- versus high-grade ccRCC classification was compared against CT-only baselines (DINOv2-Base and DINOv2-Finetuned) and a WSI-based reference model (GigaPath-Finetuned). Cross-modal alignment was assessed using cosine similarity analysis. Results: RCC-Align achieved an AUC of 0.601 (95% CI, 0.524-0.673) and AUPRC of 0.599 (95% CI, 0.541-0.676), outperforming DINOv2-Finetuned (AUC 0.545; AUPRC 0.543) with significantly improved low-grade prediction (p = 0.004). RCC-Align also demonstrated stronger paired WSI-CT embedding alignment compared with baselines. The WSI-based GigaPath reference achieved an AUC of 0.719. Conclusion: Pathology-guided contrastive learning improves CT-based ccRCC grading while requiring only CT at inference. This approach may complement tissue diagnosis when biopsy is unsafe, infeasible, or limited by intratumoral heterogeneity. Validation in larger, multi-institutional cohorts with external testing is needed before clinical translation.
Read the full abstract

All authors Amit Das, Tanmay Shukla, Naofumi Tomita, Faraz Farhadi, Jessica Sin, Ari Hakimi, Chad Vanderbilt, Jie-Fu Chen, Ritesh Kotecha, Weijie Ma, Bing Ren, Saeed Hassanpour

Robotics

Bend the Clock: Predicting Ahead to Beat Latency in Event-Based Object Detection

Biswadeep Sen, Benoit R. Cottereau, Nicolas Cuperlier et al. (+1 more)

Event cameras promise low-latency perception for high-speed robotic systems, where even short delays can render detections stale by the time they inform downstream robotic decisions. Yet modern event detectors still require tens of milliseconds of computation before their predictions become available. Conventional evaluation ignores this delay by comparing predictions with annotations at the observation timestamp, even though the scene may have changed by the time those predictions are produced. We study this observation-availability mismatch in event-based multi-object detection and show that state-of-the-art event detectors degrade substantially when evaluated at prediction availability rather than observation time. To address this, we introduce ChronoFuse, a causal availability-time detector that predicts object states for when its output becomes available rather than for when its input was observed. ChronoFuse performs causal cross-time fusion over a multi-scale feature hierarchy, combining current representations with cached temporal features to expose short-term temporal cues without using future observations. The fusion pathway is lightweight, adding only 0.17 million parameters and 0.84 ms of mean end-to-end latency overhead. ChronoFuse recovers 71% of the accuracy lost to latency on 1Mpx driving data and 90.8% under rapid drone motion on FRED, nearly restoring zero-delay performance. Under the extreme motion of EV-Flying, ChronoFuse reaches 20.95 sAP, compared with 2.25 for the strongest standard event detector (9.3x gain). These results show that predicting ahead can be critical for robots operating in fast-changing scenes, including autonomous driving, agile flight, and robotic interception.
Read the full abstract

All authors Biswadeep Sen, Benoit R. Cottereau, Nicolas Cuperlier, Terence Sim

Machine Learning

On Preference Coverage Collapse from Hindsight Relabeling in Multi-Objective Reinforcement Learning

Baptiste Bonin, Caro Strickland and Audrey Durand

Hindsight relabeling which retroactively replacing a transition's goal with the outcome the agent actually achieved is an effective tool for improving sample-efficiency in Reinforcement Learning (RL). A natural extension to preference-conditioned multi-objective RL (MORL) relabels transitions with the preference direction the agent achieved rather than the one asked for. We show that this extension is frequently harmful: across four preference-conditioned off-policy algorithms spanning two critic backbones and two preference-sampling schemes on the continuous-control MO-Gymnasium suite, it degrades 19 of 36 algorithm-environment settings by as much as four standard deviations, improves only one, and leaves the rest unaffected. The harm is not a symptom of noisy relabels; denoising the target recovers almost nothing, and neither prioritized sampling nor any buffer-structural choice reproduces it. Instead, repeated relabeling collapses the critic's coverage onto whatever narrow region of the preference space the agent happened to visit. We name this failure mode Preference Coverage Collapse, and quantify it with abandoned preference mass (APM), a value-aware statistic that tracks the harm ($\rho = -0.73$) where a purely structural coverage count does not. We then introduce her\_mix, a single-parameter convex combination pulling the achieved direction back towards the requested preference. At one fixed value across every algorithm and environment, it returns 16 of the 19 harmed settings to baseline, preserves and even improves the one setting in which relabeling helps, and cuts abandoned preference mass from $69\%$ to $6\%$. Protecting coverage over the preference simplex, not filtering noisy relabels, is what makes hindsight relabeling safe for MORL.
Read the full abstract

Computation and Language

COMED: The Missing Middle Between Routing and Collaboration in Multi-LLM Inference

Norah Alballa, Wenxuan Zhang, Salma Kharrat et al. (+4 more)

No single Large Language Model (LLM) is uniformly reliable across queries, motivating multi-model inference systems that either route among models or combine their outputs. However, routing stops after selecting an initial model, while dense collaboration invokes peers on every query. We show that collaboration is non-monotonic: peers can recover failures that no model solves alone, but can also corrupt initially correct answers. We introduce COMED (Controlled Model Escalation for Multi-LLM Deliberation), a post-anchor controller for selective cross-model collaboration. COMED uses anchor self-consistency, router margin, and a lightweight peer probe to accept confident answers, verify ambiguous cases, and escalate only when collaboration is likely beneficial. We formalize this trade-off with a rescue-harm decomposition showing that selective collaboration improves when rescued errors outweigh collaboration-induced harms. Across medical, scientific, and general reasoning benchmarks, COMED improves fixed and routed anchors in all 16 open-weight settings, with gains up to +10.7 percentage points on MedQA while invoking fewer models and using fewer decoded tokens than dense collaboration. On HLE with frontier models, COMED improves GPT-5.5 from 23.1% to 28.1%, outperforming dense collaboration and achieving the best results.
Read the full abstract

All authors Norah Alballa, Wenxuan Zhang, Salma Kharrat, Fares Fourati, Zafar Ayyub Qazi, Mohamed Elhoseiny, Marco Canini

Artificial Intelligence

TwinCheck: Evidence-Grounded Negative-Twin Verification for Stateful Tool Agents

Jiaxuan Dai and Tianyi Huang

A single locally plausible tool call can derail an otherwise successful agent trajectory. Suspicion alone does not justify intervention, because the replacement itself can introduce the very failure verification is meant to prevent. We introduce TwinCheck, an inference-time verification policy that considers replacement only when the trace satisfies an evidence condition tied to a trace-local failure hypothesis. It constructs a trace-grounded counterfactual alternative, a negative twin, and replaces the agent's proposal only if the twin passes structural checks and the pairwise verifier prefers it in both candidate orders. For paired evaluation, exact replay holds the agent's parsed responses and actions fixed until the first accepted replacement, separating intervention effects from resampling. In the primary analysis of 159 multi-turn BFCL V4 tasks with complete exact-replay pairs, the complete policy raises task success for GPT-5.6 Sol from 45.3% to 58.5% (95% task-bootstrap CI [8.2, 18.8]), with no observed success-to-failure regressions. Together, these findings recast execution-boundary repair as a constrained comparison, making the counterfactual action itself the object of verification.
Read the full abstract

Multimedia

Small Cues, Big Consequences: Learning Pivotal Cues for Multimodal Meme Classification

Akshit Sharma and Prashant W. Patil

Memes often derive their harmful, hateful, or sarcastic meaning from small but decisive visual, textual, or cross-modal cues. Existing multimodal classifiers can miss such evidence when relying mainly on global image-text representations. We introduce MemeCF, a cue-focused benchmark of 9,895 memes across harm, hate, and sarcasm, with annotations identifying the modality and rationale of the pivotal evidence. We also propose MemePIVOT, a local-global architecture for meme classification. MemePIVOT uses frozen CLIP features, unbalanced optimal transport to align words with image patches while allowing irrelevant evidence to remain unmatched, and an evidential fusion head to combine local grounding with global meme context under uncertainty. Experiments on HarMeme, PrideMM, and MemeCF show consistent gains over strong text-only, image-only, multimodal, and vision-language baselines. Cross-dataset and ablation results further show that explicit pivotal-evidence modeling improves robustness and contributes meaningfully beyond global multimodal representations. Our code and dataset are publicly available at https://github.com/AkshitSharma1/MemePIVOT
Read the full abstract

Systems and Control

Impact-Time Guidance via Normal Contraction to a Time-to-Go Isochron

Shivam Bajpai and Abhinav Sinha

We develop a contraction-based perspective on impact-time guidance that augments a baseline homing command with a timing bias. The proposed perspective treats the prescribed schedule as a moving time-to-go isochron and regulates motion normal to that set through velocity-normal lateral acceleration while the interceptor's speed remains constant. We derive a transport equation that characterizes homing-compatible time-to-go coordinates and define a predictor defect that quantifies the mismatch of approximate maps. We show that the scalar timing channel induces a coordinate-invariant rank-one metric on the normal quotient. To account for bounded lateral acceleration, we formulate a robust scalar filter and derive a necessary and sufficient condition for pointwise feasibility. We then show that terminal calibration and funnel invariance establish first interception at the prescribed time under the stated assumptions. We also develop a preterminal alignment and homing handover that avoids singular inversion as lateral timing authority vanishes near collision-course alignment. The proposed perspective accommodates analytic, numerical, and learned time-to-go maps that satisfy the required calibration and regularity conditions.
Read the full abstract

Machine Learning

CORE-STACK+: Meta-Learning for Deep Stacked Generalization

Noor Islam S. Mohammad

Stacking heterogeneous vision backbones (CNNs, ViTs, and hybrids) is the de facto recipe for accuracy, calibration, and robustness, yet two coupled pathologies limit its returns. Prediction-space multicollinearity ill-conditions the meta-learner's Gram matrix, inflating weight variance and producing brittle solutions on a thin manifold. Calibration collapse compounds constituent miscalibration through naive linear stacking, so adding more models can hurt expected calibration error (ECE). Existing remedies, ridge regularization, greedy selection, model soups, and SWAG address at most one of these issues, and none jointly target conditioning and calibration in heterogeneous prediction pools. We introduce CORE-STACK+, a preconditioning pipeline with four components: (i) a kernelized redundancy filter that removes non-linear inter-model dependencies invisible to Pearson correlation, using Centered Kernel Alignment (CKA) [23]; (ii) a $<15$K-parameter differentiable meta-feature gate that learns per-sample attention over ensemble statistics; (iii) a spectrum-adaptive Ridge penalty $lambda^{star}=lmax(Chat)/SNR(Chat)$ derived from a Marchenko-Pastur signal-noise decomposition, eliminating nested cross-validation; and (iv) a Laplace-approximate Bayesian blender replacing inverse-RMSE heuristics. We prove a PAC-Bayes excess-risk bound that, for the first time, jointly accounts for prediction-space redundancy and meta-learner capacity. Across six benchmarks, CORE-STACK+ delivers $+1.8\%$ top-1 on ImageNet-1K, $-4.2$ mCE on ImageNet-C, $+0.9$ mIoU on ADE20K, and $+1.3$ AP on COCO, while reducing retained models by 35-57% and inference FLOPs by up to $41%$. ECE improves $2.1\times$ over deep ensembles without post hoc temperature scaling.
Read the full abstract

Cryptography and Security

Ajar: Measuring Open Privilege in Agent Defenses

Reshabh K Sharma, Linxi Jiang, Shuo Chen et al. (+1 more)

A language model agent acts through the tools it is given. The data it reads while working on a task can redirect what it does with those tools. A growing set of techniques for safe and secure agent execution therefore sits between the agent and its tools, aiming to enforce access control, information flow or isolation at that boundary. Today these techniques are evaluated on agent-security benchmarks built around indirect prompt injection. Those benchmarks judge a defense by how far it brings the number of successful attacks down while preserving the agent's utility. A defense is judged only on the agent's execution. It can score well on both metrics while holding open a transfer, a deletion or a broad read that no task needed. Ajar measures that open privilege directly using the existing benchmarks. It attaches to an agent-security benchmark that already exists and reuses the tasks, tool schemas, reference solutions and goal states that benchmark uses to grade its own runs. For each benign task it builds candidate tool calls the task does not need, so allowing one is privilege left open. These calls are presented to the defense at every point where the agent could act. We evaluate Ajar by attaching it to AgentDojo, where open privilege becomes a third axis beside the existing attack success and benign utility. We run it on five defenses: Progent, CaMeL, AC4A, Permission Assistant, and Claude Code's Auto mode. We observed that they leave widely different amounts of privilege open. Two defenses leak by almost the same amount yet differ widely in the benign tasks they finish, and one defense buys part of its tightness by refusing calls its tasks were entitled to make. This open privilege cannot be derived from the measured attack success or benign utility. The source code of Ajar is available at https://github.com/reSHARMA/Ajar.
Read the full abstract

All authors Reshabh K Sharma, Linxi Jiang, Shuo Chen, Zhiqiang Lin

Cryptography and Security

ACTS: A multi-tier benchmark evaluating LLM cipher identification under controlled blind conditions

Youssef Hamdi Zafaan Ibrahim and Mohammed Khalaf Salama

We introduce ACTS (Artifacts in Cipher Testing Suite), a reproducible benchmark that isolates cryptanalytic ability through tiered metadata deprivation (Tier-1: full metadata; Tier-2: filename only; Tier-3: completely blind) and tests forced reasoning (Tier-5: chain-of-thought, code-as-reasoning, self-correction) on ciphertext alone. A 10-configuration ablation study on 7,000 files, using a single 70/30 train-test split for feature-removal analysis, provides additional evidence at scale. Live API inference on a v2b corpus with fully randomised padding (PKCS7, ISO 10126, and ANSI X9.23 selected per file), unique CSPRNG keys, and unique plaintexts (127 files per model, 381 Tier-1 records, 380 Tier-3 records across three cloud systems, supplemented by 254 autonomous agentic evaluations in Tier-4) yields a combined Tier-3 accuracy of 30.8%, only modestly above the 14.3% random baseline for seven-way classification. The corresponding combined metadata-dependency gap is 40.9 percentage points (Tier-1: 71.7% vs. Tier-3: 30.8%). Against a classical Random Forest (69.2% on 7,000 files, trained on engineered byte-level features), the observed live gap is 38.4 percentage points. Because this comparison spans different input representations and training paradigms, the gap should be interpreted as an overall capability difference rather than a clean factorial decomposition. Six findings are reported: (1) Metadata dependency remains large; (2) Scaling failure under blind conditions; (3) Forced reasoning is epiphenomenal; (4) The observed live capability gap exceeds earlier heuristic estimates; (5) The signal is primarily structural rather than statistical; (6) Heuristic invariance versus ML fragility reveals different failure modes.
Read the full abstract

Artificial Intelligence

Harness as a Language: A Minimalist Agent Framework With Maximal Expressivity

Zhening Li, Joshua Liu, Mateja Vukelic et al. (+7 more)

Modern language-model agents are built around the agent loop: the LLM is placed in an environment exposing a set of tools, and the LLM has full control over the workflow by alternating between tool calls and observing their output. However, certain capabilities such as long-term memory and self-improvement currently require specialized systems beyond the agent loop itself. We built an LLM agent framework, JAZ, to explore the extent to which a minimal harness that is little more than the agent loop itself can accomplish tasks these specialized systems are built for. JAZ exposes a single LLM-based primitive `invoke` and provides a set of built-in hooks that allow the programmer to apply constraints and perform monitoring. Generalizing existing code-mode agent loops, `invoke` is the simplest loop that satisfies two defining properties: (1) the LLM can write arbitrary executable code that can include recursive `invoke`; (2) everything visible to the LLM - all inputs to `invoke` as well as its interaction history with the code environment - are variables in the code environment. We motivate our design from first principles, viewing `invoke` as a language primitive representing a function whose implementation is provided at runtime by an LLM every time it is called. To validate the design of our core `invoke` primitive, we evaluate `invoke` - with only prompting, no manually designed tools, harness, or external systems (e.g., memory or the file system) - on workflows traditionally implemented through specialized harnesses. On long-horizon workflows requiring recall far beyond the context window, JAZ `invoke` outperforms Letta (MemGPT) by 8% at half its cost on the recall-heavy portion of StuLife. On continual self-improvement, JAZ `invoke` outperforms ACE by 4% at a lower cost on AppWorld.
Read the full abstract

All authors Zhening Li, Joshua Liu, Mateja Vukelic, Nicole Shen, Supriya Lall, Amitayush Thakur, Alex Zhang, Omar Khattab, Jonathan Light, Armando Solar-Lezama

Machine Learning

PR-Smoother: Simulator-Preserving Non-Gaussian Smoothing for Data Assimilation

Yuta Tarumi

Many physical data assimilation (DA) workflows require smoothing methods that represent non-Gaussian posteriors over physical state variables, scale to high-dimensional simulators, train from observation windows alone, and remain compatible with calibration of the prescribed simulator. We introduce PR-Smoother, a simulator-preserving amortized smoother designed for this prescribed-simulator DA regime. Its key design principle is to keep the prescribed simulator explicit in both the evidence lower bound and the variational family: rather than learning replacement dynamics or a learned trajectory prior, PR-Smoother learns only future-conditioned corrections around the prescribed rollout. This yields an explicit non-Gaussian smoothing distribution over physical trajectories and supports joint state, parameter, and sensor-bias learning from observations alone. The variational family contains the exact smoother in deterministic and linear-Gaussian limits. Empirically, PR-Smoother captures multimodal posteriors in 4-dimensional Lorenz-96, remains accurate under ambiguous nonlinear observations and process noise in 40-dimensional Lorenz-96, and scales to joint state-parameter-bias inference in 16,384-dimensional Kolmogorov flow.
Read the full abstract

Data Structures and Algorithms · Cross-listed from math.OC

Silver Rate Is (Almost) Optimal for Gradient Descent: The Strongly Convex Case

Kaizhao Liu and Yuhan Ye

We study gradient descent with predetermined nonnegative stepsizes on smooth strongly convex functions. Let $p_{\mathrm{sil}}=\log_2(1+\sqrt2)$ and $\kappa$ be the condition number. We prove the iteration lower bound $\Omega\left(\kappa^{\frac{1}{p_{\mathrm{sil}}}-o(1)}\log\frac1\delta\right)$ for both relative squared distance and relative function error, uniformly over $0<\delta<1$ and sufficiently large $\kappa$. This matches the polynomial exponent of $\kappa$ for the Silver stepsize schedule established in [Altschuler and Parrilo, 2025].
Read the full abstract

Robotics

MSK-Bench: Benchmarking Full-Body Musculoskeletal Motor Control Across Tasks, Control Paradigms, and Physiological Metrics

Mengtao Ou, Zongzheng Zhang, Zhenghao Xiao et al. (+7 more)

Musculoskeletal (MSK) humanoids provide a physiologically grounded embodiment for studying full-body motor control, but their high-dimensional muscle actuation, delayed activation dynamics, and redundant muscle–tendon structures make learning substantially harder than torque-driven humanoid control. Existing MSK benchmarks remain fragmented across gait, prosthetics, dexterous hands, or challenge-specific tracks, leaving full-body muscle-actuated control insufficiently evaluated under standardized tasks, methods, and metrics. We introduce MSK-Bench, a benchmark of 22 full-body motor-control tasks organized into three progressively challenging categories: postural stabilization, common locomotor behaviors, and contact-rich environmental interaction. Under unified task protocols and robustness perturbations, MSK-Bench evaluates 5 representative control paradigms, including reward-based RL, agentic reward tuning, latent-action RL, imitation-prior control, and residual adaptation over imitation priors. Beyond task success and reward, MSK-Bench further reports robustness analysis and physiology-oriented diagnostics, including activation cost, joint smoothness, and EMG-envelope similarity. Our empirical study shows that embodiment-aware exploration and structured action representations improve task coverage in high-dimensional muscle spaces, imitation priors enhance reference-compatible stabilization and locomotion but degrade under contact-rich terrain mismatch, and residual adaptation can recover successful behaviors when fixed references fail. We further find that improved task success does not necessarily imply improved physiological agreement, highlighting the importance of evaluating task performance, robustness, and physiological behavior jointly. MSK-Bench provides a task–method–metric testbed for full-body muscle-actuated humanoid control.
Read the full abstract

All authors Mengtao Ou, Zongzheng Zhang, Zhenghao Xiao, Yixuan Pan, Ziwen Zhuang, Hang Zhao, Hongyang Li, Yanan Sui, Libin Liu, Hao Zhao

Robotics

Backdoors in Learning-Based Industrial Robotic Arm Manipulation: An Empirical Security Study

Zijian Zhang, Zhen Zeng, Zhongshu Gu et al. (+1 more)

Learning-based models (e.g., visuomotor and Vision-Language-Action (VLA)) are increasingly explored for industrial robotic manipulation, where model predictions are directly translated into physical actions. This tight coupling between model behavior and physical execution makes hidden security vulnerabilities particularly consequential. While backdoor attacks have been widely studied in conventional AI models, their effects on deployed learning-based robotic arm manipulation systems remain less understood: a backdoored robot can behave normally during benign operation while inducing attacker-specified behaviors only when specific triggers are present, posing potentially serious risks in physical environments. In this work, we present a preliminary empirical security study of backdoor attacks and defenses in learning-based robotic manipulation on two real commercial industrial robotic arms (FANUC and xArm). We investigate whether a backdoor can reliably induce semantically incorrect manipulation behaviors while remaining stealthy under nominal task execution. We then develop an online defense pipeline that detects and neutralizes triggers at runtime, and compare its effectiveness against an offline fine-tuning defense. Beyond defense effectiveness, we further evaluate the computational latency and execution overhead introduced by the defense pipeline to assess its suitability for high-throughput industrial operation.
Read the full abstract

All authors Zijian Zhang, Zhen Zeng, Zhongshu Gu, Sandeep Pisharody

Machine Learning

Marginally Correct Tool Caches Can Reverse Group-Normalized Policy Updates

Shivam Gupta

Tool-result caching reduces repeated execution in agent training, but also couples rollout randomness. We study a two-action model in which independent and shared execution preserve every rollout's conditional reward distribution. Despite this marginal agreement, sharing one stochastic result per group can reverse the expected group-normalized policy update. We derive an exact finite-group expression: against a constant alternative, the shared update follows the probability of winning minus the probability of losing, rather than the difference in expected reward. A Bernoulli specialization yields a wrong-direction region and a non-vanishing update-variance floor as group size grows. Centering without group standard-deviation scaling preserves the expected-return direction in this model, using an existing estimator control. Exhaustive finite sums verify 540 configurations and 3,240 estimator evaluations, with a separate ordered-sequence checker. An implementation audit reproduces the sharing path in a pinned, unmodified TVCache stack using 256 scripted rollouts. These results do not measure language-model training performance or refute TVCache's deterministic-output contract. They establish that marginal output validity alone cannot certify a stochastic cache as training-equivalent.
Read the full abstract